Importance of negative sampling in weak label learning
This work addresses a specific bottleneck in weak-label learning for domains like image and audio classification, but it is incremental as it builds on existing sampling strategies.
The paper tackles the problem of selecting informative negative instances in weak-label learning, where only bag labels are known, and shows that their method improves classification performance and reduces computational cost on CIFAR-10 and AudioSet datasets compared to random sampling.
Weak-label learning is a challenging task that requires learning from data "bags" containing positive and negative instances, but only the bag labels are known. The pool of negative instances is usually larger than positive instances, thus making selecting the most informative negative instance critical for performance. Such a selection strategy for negative instances from each bag is an open problem that has not been well studied for weak-label learning. In this paper, we study several sampling strategies that can measure the usefulness of negative instances for weak-label learning and select them accordingly. We test our method on CIFAR-10 and AudioSet datasets and show that it improves the weak-label classification performance and reduces the computational cost compared to random sampling methods. Our work reveals that negative instances are not all equally irrelevant, and selecting them wisely can benefit weak-label learning.